48 个项目
gdm-concordia
A library for building a generative model of social interacions.
chex
Chex: Testing made fun, in JAX!
dm-control
Continuous control environments and MuJoCo Python bindings.
mujoco-mjx
MuJoCo XLA (MJX)
mujoco
MuJoCo Physics Simulator
treescope
Treescope: An interactive HTML pretty-printer for ML research in IPython notebooks.
penzai
Penzai: A JAX research toolkit for building, editing, and visualizing neural networks.
dm-clrs
The CLRS Algorithmic Reasoning Benchmark.
optax
A gradient processing and optimisation library in JAX.
dm-pix
PIX is an image processing library in JAX, for JAX.
dm-meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
open-spiel
A Framework for Reinforcement Learning in Games
dm-robotics-transformations
A library for Rigid Body Transformations
dm-robotics-moma
Tools for authoring robotic manipulation tasks.
dm-robotics-manipulation
Parametrically defined mesh objects
dm-robotics-geometry
This library provides primitives for dealing with scene and robot geometry
dm-robotics-controllers
Python bindings for dm_robotics/cpp/controllers
dm-robotics-agentflow
Tools for single-embodiment, multiple-task, Reinforcement Learning
dm-haiku
Haiku is a library for building neural networks in JAX.
dm-reverb-nightly
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research.
envlogger
EnvLogger: A tool for recording trajectories.
dm-sonnet
Sonnet is a library for building neural networks in TensorFlow.
xmanager
A framework for managing machine learning experiments
dm-reverb
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research.
distrax
Distrax: Probability distributions in JAX.
mujoco-dev
MuJoCo Physics Simulator (unstable dev build) [DEPRECATED - DO NOT USE]
dm-env-rpc
A networking protocol for agent-environment communication.
dmlab2d
fancyflags
A Python library for defining dictionary-valued flags.
rlax
A library of reinforcement learning building blocks in JAX.
android-env
AndroidEnv environment and library for training agents.
rlds
A Python library for Reinforcement Learning Datasets.
dm-launchpad-nightly
Launchpad is a library that simplifies writing distributed programs and seamlessly launching them on a range of supported platforms.
jmp
JMP is a Mixed Precision library for JAX.
dm-env
A Python interface for Reinforcement Learning environments.
dm-tree
Tree is a library for working with nested data structures.
labmaze
LabMaze: DeepMind Lab's text maze generator.
jraph
Jraph: A library for Graph Neural Networks in Jax
PySC2
Starcraft II environment and library for training agents.
dm-launchpad
Launchpad is a library that simplifies writing distributed programs and seamlessly launching them on a range of supported platforms.
dm-acme
A Python library for Reinforcement Learning.
trfl
trfl is a library of building blocks for reinforcement learning algorithms.
dm-memorytasks
DeepMind Memory Tasks, a set of Unity-based machine-learning research tasks.
alphafold
An implementation of the inference pipeline of AlphaFold v2.0.This is a completely new model that was entered as AlphaFold2 in CASP14 and published in Nature.
bsuite
Core RL Behaviour Suite. A collection of reinforcement learning experiments.
graph-nets
Library for building graph networks in Tensorflow and Sonnet.
dm-sonnet-gpu
Sonnet is a library for building neural networks in TensorFlow.
mathematics-dataset
A synthetic dataset of school-level mathematics questions